mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-06-29 23:41:12 +08:00
Add warning log when metadata query hits 10000 result limit (#14109)
## What problem does this PR solve? Add a warning log when `get_flatted_meta_by_kbs` returns 10,000 results, which indicates the query limit has been reached and metadata may be silently truncated. ## Type of change - [x] Improvement (non-breaking change which improves observability)
This commit is contained in:
@@ -733,9 +733,11 @@ class DocMetadataService:
|
||||
|
||||
# Aggregate metadata
|
||||
meta = {}
|
||||
doc_count = 0
|
||||
|
||||
# Use helper to iterate over results in any format
|
||||
for doc_id, doc in cls._iter_search_results(results):
|
||||
doc_count += 1
|
||||
# Extract metadata fields (exclude system fields)
|
||||
doc_meta = cls._extract_metadata(doc)
|
||||
|
||||
@@ -752,6 +754,9 @@ class DocMetadataService:
|
||||
meta[k][sv] = []
|
||||
meta[k][sv].append(doc_id)
|
||||
|
||||
if doc_count >= 10000:
|
||||
logging.warning(f"[get_flatted_meta_by_kbs] Results hit the 10000 limit for KBs {kb_ids}.")
|
||||
|
||||
logging.debug(f"[get_flatted_meta_by_kbs] KBs: {kb_ids}, Returning metadata: {meta}")
|
||||
return meta
|
||||
|
||||
|
||||
Reference in New Issue
Block a user